© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201182
    Prev
    Next
    INDEX
    Explanations

    mathematics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     زر
    0.42
    ieso
    0.40
     उर्वर
    0.40
     hí
    0.39
    itha
    0.39
                           
    0.38
    鄒
    0.38
                          
    0.37
    eat
    0.37
     complementar
    0.36
    POSITIVE LOGITS
    steins
    0.42
     graces
    0.40
    avimo
    0.38
     médecine
    0.38
     cams
    0.37
    ້ນ
    0.37
    Bod
    0.36
    ਾਮ
    0.36
    戊
    0.36
     kon
    0.35
    Activations Density 0.000%

    No Known Activations